Commit Graph
71 Commits
Author SHA1 Message Date
ricoromaandClaude Opus 5.5 a676a520b0 docs: plan the second scaling-improvement measurement attempt
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 16:30:27 +03:00
ricoromaandClaude Opus 5.5 056ca19a53 docs: format probe script in connection cost evidence
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 15:46:34 +03:00
ricoromaandClaude Opus 5.5 8b69913995 docs: report scaling-improvement pool result for track 1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 15:46:24 +03:00
ricoromaandClaude Opus 5.5 1694b1d0ae docs: add scaling-improvement comparisons, connection cost and checks
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 15:46:13 +03:00
ricoromaandClaude Opus 5.5 cd88b48b41 docs: add scaling-db-nooverflow label
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 15:30:47 +03:00
ricoroma 53eb38e19b Revert "revert: measure scaling-improvement baseline without the pool change"
This reverts commit 62fa57535e.
2026-10-11 15:04:46 +03:00
ricoroma dfd9ecce29 docs: add scaling-db-before bench evidence 2026-10-11 15:04:46 +03:00
ricoromaandClaude Opus 5.5 3df111cd80 docs: add scaling db A/A label for scaling-improvement
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 14:37:29 +03:00
ricoromaandClaude Opus 5.5 62fa57535e revert: measure scaling-improvement baseline without the pool change
This reverts commits 9c3959d, 623a973 and 80e64cd.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 14:10:43 +03:00
ricoromaandClaude Opus 5.5 1bb8ea67ad feat: add two-cell db4 series for the scaling-improvement measurements
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 14:06:57 +03:00
ricoromaandClaude Opus 5.5 80e64cda4a test: count PostgreSQL sessions without healthcheck and flush races
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 13:46:39 +03:00
ricoromaandClaude Opus 5.5 623a973dac test: wait for PostgreSQL session stats before counting pool reconnections
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 13:30:38 +03:00
ricoromaandClaude Opus 5.5 9c3959d768 perf: keep a fixed PostgreSQL pool without overflow connections
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 13:25:26 +03:00
ricoromaandClaude Opus 5.5 0b0421ad2f docs: record track 1 improvement hypothesis H4
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 13:23:49 +03:00
ricoromaandClaude Opus 5.5 1e50a4a3fc feat: compare PostgreSQL sessions and connections in track 1 series
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 13:23:12 +03:00
ricoromaandClaude Opus 5.5 029aa3be82 docs: propose scaling-improvement change
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 13:19:56 +03:00
ricoromaandClaude Opus 5.5 bbd6f65316 chore: archive scaling-bench change
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 12:25:18 +03:00
ricoromaandClaude Opus 5.5 dedb8ba0fa docs: report PostgreSQL saturation series db and rubric answer
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 12:24:17 +03:00
ricoromaandClaude Opus 5.5 195a3f8ad9 docs: add series db plots and host check
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 12:22:45 +03:00
ricoromaandClaude Opus 5.5 9fbe2ea503 feat: draw series db in R* plot and summarize PostgreSQL saturation
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 12:22:32 +03:00
ricoromaandClaude Opus 5.5 48d10dad37 docs: add scaling series db
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 12:21:04 +03:00
ricoromaandClaude Opus 5.5 46e8f75a2c docs: record series db calibration in scaling-bench design
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 11:31:39 +03:00
ricoromaandClaude Opus 5.5 95539a1883 feat: add track 1 series db with a tight PostgreSQL CPU limit
Configs may carry a fifth element, the PostgreSQL CPU limit, which goes
into the config key (-pg<CPU>), the budget and the cell stand. Series db:
1, 2, 4 replicas at the tight limit and a 4 x 1 control at 2 CPU; label
summaries show PostgreSQL CPU at R* against its limit and throttling.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 11:27:30 +03:00
ricoromaandClaude Opus 5.5 a3279374f7 docs: fix scaling-bench verify findings in report, design and rules
Close the 53300 known issue, restate H1 and saturation conclusions
against the pre-registered criteria and grid resolution, name the
unresolved host mechanism, attribute overload 503 to the pool timeout,
and plan a fresh A/A for scaling-improvement.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 07:36:33 +03:00
ricoromaandClaude Opus 5.5 4abedaed78 docs: add 53300 evidence, regression and regenerated track 1 summaries
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 07:35:49 +03:00
ricoromaandClaude Opus 5.5 dcea85942a feat: add cost and memory tables, passports and sampler limits to track 1 outputs
plots.py summary gains per-request CPU by component, PostgreSQL waits and
pool, H1b throttling and memory peaks; compare.py and plots.py headers
name the spec, change and host; errors logs match 5xx by status field and
keep the exception tail; series labels record sampler limits.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 07:26:36 +03:00
ricoromaandClaude Opus 5.5 68edc66742 fix: answer 503 when PostgreSQL refuses connections with too many clients
SQLSTATE 53300 (too_many_connections) joins UNAVAILABLE_SQLSTATES, so a
refused pool connection gives 503 unavailable instead of 500. New fault
check fills max_connections through the failure stand hook and expects
503 in the contract format.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 07:26:36 +03:00
ricoromaandClaude Opus 5.5 ca0817390f docs: report track 1 scaling series
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 06:49:49 +03:00
ricoromaandClaude Opus 5.5 0ea787ccae docs: add scaling-bench plots and comparisons
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 06:49:03 +03:00
ricoromaandClaude Opus 5.5 bfc5eb8ede docs: add scaling A/A label
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 06:48:19 +03:00
ricoromaandClaude Opus 5.5 0479789aa3 docs: add scaling series plots for A and B
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 06:26:38 +03:00
ricoromaandClaude Opus 5.5 7b6a31b62a docs: record 500 instead of 503 on too many clients found by the pool series
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 06:26:30 +03:00
ricoromaandClaude Opus 5.5 b7e787a658 fix: move reference line labels off the bars in the scaling plots
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 06:26:03 +03:00
ricoromaandClaude Opus 5.5 f65a8e86d1 docs: add scaling pool series
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 06:26:03 +03:00
ricoromaandClaude Opus 5.5 1320584d9f docs: add scaling series B
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 06:01:52 +03:00
ricoromaandClaude Opus 5.5 3401388b5e docs: describe track 1 series in AGENTS.md
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 04:47:04 +03:00
ricoromaandClaude Opus 5.5 71359be0fb docs: add scaling series A
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 04:47:04 +03:00
ricoromaandClaude Opus 5.5 cbe3b4a43b docs: add scaling-bench self-checks
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 04:10:02 +03:00
ricoromaandClaude Opus 5.5 712d2450e4 fix: preallocate all k6 VUs in track 1 steps so the generator does not drop iterations near R*
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 03:55:21 +03:00
ricoromaandClaude Opus 5.5 68eef77119 fix: put the growth series end label above its whisker in the R* plot
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 03:45:46 +03:00
ricoromaandClaude Opus 5.5 5de4da997c fix: drop the resume image warning, the containerd image id changes on every build
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 03:44:41 +03:00
ricoromaandClaude Opus 5.5 02fd3d8a36 feat: add track 1 scaling series to the bench stand
Series a/b/pool/ab/quick in bench/run.py: per-cell fresh stand with the
configuration's replicas and max_connections, open-model mixed profile
(k6/mixed.js), fixed levels and R* search by SLO, a sampler container
for cgroup, VM, HAProxy and PostgreSQL metrics, resume and a stand
lock. Pure helpers in bench/scaling.py, SVG plots in bench/plots.py,
series mode for bench_compare and bench_ab. Hypotheses H1-H3 go to
REPORT.md before the first series.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 03:28:36 +03:00
ricoromaandClaude Opus 5.5 525ace7c9b docs: propose scaling-bench change
Track 1 "cost of scaling": open-model series A (fixed 4 CPU budget),
B (1-6 replicas), pool border (max_connections 100 vs 50) and A/A,
sampler of cgroup/VM/LB/PostgreSQL metrics, generator limits, series
mode for bench_compare and bench_ab. Hypotheses H1-H3 are recorded in
the design before any series run.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 02:48:40 +03:00
ricoromaandClaude Opus 5.5 84ee13ca5a chore: archive rolling-update change
Sync the rolling-update delta specs into db-migrations,
graceful-shutdown, load-balancing and load-benchmark, move the change to
the archive, mark it in PLAN.md and update the transitional state and
code map in AGENTS.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:59:19 +03:00
ricoromaandClaude Opus 5.5 6f85d21f3b docs: retake rolling-update evidence on the final verify commit
Re-run the compatibility walk-through, the script failure cases with a
real Ctrl+C through a pseudo-terminal, the stand lifecycle after
replacement and the quick rollout and failover self-checks on 84161c0
with a clean tree; update the report rows and limitations.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:56:30 +03:00
ricoromaandClaude Opus 5.5 84161c033a fix: keep migration lock timeout below the app statement timeout
With lock_timeout equal to statement_timeout (5 s) every request queued
behind a migration waiting for its lock failed with 503 together with
the migration. A 2 s lock timeout lets the queue proceed once the
migration gives up.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:38:10 +03:00
ricoromaandClaude Opus 5.5 5e102e6d0c fix: harden rolling update cleanup and preconditions found in verify
Reset the new replica ID before entering the starting state and let the
cleanup find a replica created by an interrupted compose scale; refuse
to start while LB slots keep a manual drain or maint state; log the exit
code of each stopped old replica and print full LB commands for manual
cleanup. Document the migrate step and the rollback tag limitation.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:33:33 +03:00
ricoromaandClaude Opus 5.5 69ebf5cd38 docs: add rolling-update baseline measurement and report
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:21:34 +03:00
ricoromaandClaude Opus 5.5 9dcea0b2b8 docs: add rolling-update regression evidence and report sections
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:17:34 +03:00
ricoromaandClaude Opus 5.5 de654a1c83 fix: recreate the migrate service container during rolling update
A one-off run --rm left the migrate container of the previous image in
the stand; scripts/restart.sh then started it as a dependency of api and
the old migrations failed on the newer schema, so test-persistence broke.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:04:50 +03:00